-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathstatis2.py
226 lines (200 loc) · 11.4 KB
/
statis2.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
import geopandas as gpd
import pandas as pd
import os
def statis():
year_list = []
county_list = []
GT_len_list = []
match0001_list = []
match005_list = []
match001_list = []
match05_list = []
match01_list = []
for year in [2017,2021]:
for county in ['xixiangxian','shufuxian','guanghexian','danfengxian','jiangzixian','honghexian','liboxian','linquanxian','jingyuxian','lingqiuxian']:
if not os.path.exists('b2/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp'):
continue
gdf_A = gpd.read_file('GT/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp')
gdf_C = gpd.read_file('results/'+county+'_'+str(year)+'_'+'OSM_2'+'.shp')
year_list.append(year)
county_list.append(county)
GT_len_list.append(len(gdf_A))
# for thresh in [0.0001,0.005,0.001,0.05,0.01]:
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.0001]
# print(thresh, len(tmp_list)/len((gdf_A)))
match0001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.005]
match005_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.001]
match001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.05]
match05_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.01]
match01_list.append(float(len(tmp_list)/len(gdf_A)))
pd_dict = pd.DataFrame({'year':year_list,'county':county_list,'GT_len':GT_len_list,'m0001':match0001_list,'m005':match005_list, \
'm001':match001_list,'m05':match05_list,'m01':match01_list})
pd_dict.to_csv('first10_intersec_OSM_2.csv', index=False)
year_list = []
county_list = []
GT_len_list = []
match0001_list = []
match005_list = []
match001_list = []
match05_list = []
match01_list = []
for year in [2017,2021]:
for county in ['xixiangxian','shufuxian','guanghexian','danfengxian','jiangzixian','honghexian','liboxian','linquanxian','jingyuxian','lingqiuxian']:
if not os.path.exists('b2/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp'):
continue
gdf_A = gpd.read_file('GT/'+county+'_'+str(year)+'_nodes_degree_gt_3.shp')
gdf_C = gpd.read_file('results/'+county+'_'+str(year)+'_'+'OSM_3'+'.shp')
year_list.append(year)
county_list.append(county)
GT_len_list.append(len(gdf_A))
# for thresh in [0.0001,0.005,0.001,0.05,0.01]:
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.0001]
# print(thresh, len(tmp_list)/len((gdf_A)))
match0001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.005]
match005_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.001]
match001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.05]
match05_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.01]
match01_list.append(float(len(tmp_list)/len(gdf_A)))
pd_dict = pd.DataFrame({'year':year_list,'county':county_list,'GT_len':GT_len_list,'m0001':match0001_list,'m005':match005_list, \
'm001':match001_list,'m05':match05_list,'m01':match01_list})
pd_dict.to_csv('first10_intersec_OSM_3.csv', index=False)
#######################################################################
year_list = []
county_list = []
GT_len_list = []
match0001_list = []
match005_list = []
match001_list = []
match05_list = []
match01_list = []
for year in [2017,2021]:
for county in ['xixiangxian','shufuxian','guanghexian','danfengxian','jiangzixian','honghexian','liboxian','linquanxian','jingyuxian','lingqiuxian']:
if not os.path.exists('b2/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp'):
continue
gdf_A = gpd.read_file('GT/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp')
gdf_C = gpd.read_file('results/'+county+'_'+str(year)+'_'+'b1_2'+'.shp')
year_list.append(year)
county_list.append(county)
GT_len_list.append(len(gdf_A))
# for thresh in [0.0001,0.005,0.001,0.05,0.01]:
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.0001]
# print(thresh, len(tmp_list)/len((gdf_A)))
match0001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.005]
match005_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.001]
match001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.05]
match05_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.01]
match01_list.append(float(len(tmp_list)/len(gdf_A)))
pd_dict = pd.DataFrame({'year':year_list,'county':county_list,'GT_len':GT_len_list,'m0001':match0001_list,'m005':match005_list, \
'm001':match001_list,'m05':match05_list,'m01':match01_list})
pd_dict.to_csv('first10_intersec_b1_2.csv', index=False)
year_list = []
county_list = []
GT_len_list = []
match0001_list = []
match005_list = []
match001_list = []
match05_list = []
match01_list = []
for year in [2017,2021]:
for county in ['xixiangxian','shufuxian','guanghexian','danfengxian','jiangzixian','honghexian','liboxian','linquanxian','jingyuxian','lingqiuxian']:
if not os.path.exists('b2/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp'):
continue
gdf_A = gpd.read_file('GT/'+county+'_'+str(year)+'_nodes_degree_gt_3.shp')
gdf_C = gpd.read_file('results/'+county+'_'+str(year)+'_'+'b1_3'+'.shp')
year_list.append(year)
county_list.append(county)
GT_len_list.append(len(gdf_A))
# for thresh in [0.0001,0.005,0.001,0.05,0.01]:
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.0001]
# print(thresh, len(tmp_list)/len((gdf_A)))
match0001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.005]
match005_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.001]
match001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.05]
match05_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.01]
match01_list.append(float(len(tmp_list)/len(gdf_A)))
pd_dict = pd.DataFrame({'year':year_list,'county':county_list,'GT_len':GT_len_list,'m0001':match0001_list,'m005':match005_list, \
'm001':match001_list,'m05':match05_list,'m01':match01_list})
pd_dict.to_csv('first10_intersec_b1_3.csv', index=False)
############################################################################################
year_list = []
county_list = []
GT_len_list = []
match0001_list = []
match005_list = []
match001_list = []
match05_list = []
match01_list = []
for year in [2017,2021]:
for county in ['xixiangxian','shufuxian','guanghexian','danfengxian','jiangzixian','honghexian','liboxian','linquanxian','jingyuxian','lingqiuxian']:
if not os.path.exists('b2/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp'):
continue
gdf_A = gpd.read_file('GT/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp')
gdf_C = gpd.read_file('results/'+county+'_'+str(year)+'_'+'b2_2'+'.shp')
year_list.append(year)
county_list.append(county)
GT_len_list.append(len(gdf_A))
# for thresh in [0.0001,0.005,0.001,0.05,0.01]:
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.0001]
# print(thresh, len(tmp_list)/len((gdf_A)))
match0001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.005]
match005_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.001]
match001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.05]
match05_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.01]
match01_list.append(float(len(tmp_list)/len(gdf_A)))
pd_dict = pd.DataFrame({'year':year_list,'county':county_list,'GT_len':GT_len_list,'m0001':match0001_list,'m005':match005_list, \
'm001':match001_list,'m05':match05_list,'m01':match01_list})
pd_dict.to_csv('first10_intersec_b2_2.csv', index=False)
year_list = []
county_list = []
GT_len_list = []
match0001_list = []
match005_list = []
match001_list = []
match05_list = []
match01_list = []
for year in [2017,2021]:
for county in ['xixiangxian','shufuxian','guanghexian','danfengxian','jiangzixian','honghexian','liboxian','linquanxian','jingyuxian','lingqiuxian']:
if not os.path.exists('b2/'+county+'_'+str(year)+'_nodes_degree_gt_2.shp'):
continue
gdf_A = gpd.read_file('GT/'+county+'_'+str(year)+'_nodes_degree_gt_3.shp')
gdf_C = gpd.read_file('results/'+county+'_'+str(year)+'_'+'b2_3'+'.shp')
year_list.append(year)
county_list.append(county)
GT_len_list.append(len(gdf_A))
# for thresh in [0.0001,0.005,0.001,0.05,0.01]:
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.0001]
# print(thresh, len(tmp_list)/len((gdf_A)))
match0001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.005]
match005_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.001]
match001_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.05]
match05_list.append(float(len(tmp_list)/len(gdf_A)))
tmp_list = [x for x in list(gdf_C['distance']) if x < 0.01]
match01_list.append(float(len(tmp_list)/len(gdf_A)))
pd_dict = pd.DataFrame({'year':year_list,'county':county_list,'GT_len':GT_len_list,'m0001':match0001_list,'m005':match005_list, \
'm001':match001_list,'m05':match05_list,'m01':match01_list})
pd_dict.to_csv('first10_intersec_b2_3.csv', index=False)
if __name__ == "__main__":
statis()